Xujuan Zhou1, Ying Wang1, Guy Tsafnat1, Enrico Coiera1, Florence T Bourgeois2, Adam G Dunn3. 1. Centre for Health Informatics, Australian Institute of Health Innovation, The University of New South Wales, Sydney, NSW 2052, Australia. 2. Division of Emergency Medicine, Boston Children's Hospital, Boston, MA, USA; Department of Pediatrics, Harvard Medical School, Boston, MA, USA; Children's Hospital Informatics Program, Boston Children's Hospital, Boston, MA, USA. 3. Centre for Health Informatics, Australian Institute of Health Innovation, The University of New South Wales, Sydney, NSW 2052, Australia. Electronic address: a.dunn@unsw.edu.au.
Abstract
OBJECTIVES: To examine the use of supervised machine learning to identify biases in evidence selection and determine if citation information can predict favorable conclusions in reviews about neuraminidase inhibitors. STUDY DESIGN AND SETTING: Reviews of neuraminidase inhibitors published during January 2005 to May 2013 were identified by searching PubMed. In a blinded evaluation, the reviews were classified as favorable if investigators agreed that they supported the use of neuraminidase inhibitors for prophylaxis or treatment of influenza. Reference lists were used to identify all unique citations to primary articles. Three classification methods were tested for their ability to predict favorable conclusions using only citation information. RESULTS: Citations to 4,574 articles were identified in 152 reviews of neuraminidase inhibitors, and 93 (61%) of these reviews were graded as favorable. Primary articles describing drug resistance were among the citations that were underrepresented in favorable reviews. The most accurate classifier predicted favorable conclusions with 96.2% accuracy, using citations to only 24 of 4,574 articles. CONCLUSION: Favorable conclusions in reviews about neuraminidase inhibitors can be predicted using only information about the articles they cite. The approach highlights how evidence exclusion shapes conclusions in reviews and provides a method to evaluate citation practices in a corpus of reviews.
OBJECTIVES: To examine the use of supervised machine learning to identify biases in evidence selection and determine if citation information can predict favorable conclusions in reviews about neuraminidase inhibitors. STUDY DESIGN AND SETTING: Reviews of neuraminidase inhibitors published during January 2005 to May 2013 were identified by searching PubMed. In a blinded evaluation, the reviews were classified as favorable if investigators agreed that they supported the use of neuraminidase inhibitors for prophylaxis or treatment of influenza. Reference lists were used to identify all unique citations to primary articles. Three classification methods were tested for their ability to predict favorable conclusions using only citation information. RESULTS: Citations to 4,574 articles were identified in 152 reviews of neuraminidase inhibitors, and 93 (61%) of these reviews were graded as favorable. Primary articles describing drug resistance were among the citations that were underrepresented in favorable reviews. The most accurate classifier predicted favorable conclusions with 96.2% accuracy, using citations to only 24 of 4,574 articles. CONCLUSION: Favorable conclusions in reviews about neuraminidase inhibitors can be predicted using only information about the articles they cite. The approach highlights how evidence exclusion shapes conclusions in reviews and provides a method to evaluate citation practices in a corpus of reviews.
Authors: Alice Fabbri; Camilla Hansen Nejstgaard; Quinn Grundy; Lisa Bero; Adam G Dunn; Annim Mohammad; Barbara Mintzes Journal: J Gen Intern Med Date: 2021-05-26 Impact factor: 5.128